RegTech / AI / B2B Lending • 2025

Explainable AI for B2B Credit Risk Assessment

Designing transparent, audit-ready AI credit decisioning UX that eliminated the "black box" problem in B2B lending reducing decision appeals by 40% and achieving full EU AI Act compliance.

40%
Fewer Appeals
28%
Officer Confidence
100%
Audit Pass Rate
EU AI
Act Compliant
Role
Lead Product Designer
Timeline
4 Months (2025)
Focus Area
AI UX / RegTech / B2B

The Situation

The "Black Box" Problem in B2B Lending

AI Decisions Without Explanation

Our B2B lending platform used a sophisticated ML model for credit risk scoring. The model performed well statistically but created a UX crisis. SMB applicants received decisions like "Application Declined" with no explanation. Loan officers could not explain decisions to regulators or customers.

  • Unexplainable Decisions 35% of declined SMBs filed appeals all citing inability to understand the decision rationale.
  • Regulatory Exposure The EU AI Act and FCA guidelines require high-risk AI systems to provide human-readable decision explanations.
  • Loan Officer Paralysis Officers could not contextualise AI scores, leading to manual overrides based on gut feel undermining the model's value.

The Explainability Gap

Model Accuracy 94%
User Trust in Decision 22%
Officer Confidence 41%

"The model is right but I can't explain why to my customer. That's a problem." Loan Officer

The Task

Designing for Two Users: Applicants & Officers

I needed to bridge the explainability gap not by simplifying the model, but by designing a UX layer that translated complex AI outputs into human-understandable, actionable narratives for two very different user types.

The SMB Applicant

"I got declined but no one can tell me why. What do I need to fix to get approved next time?"

Needs Clarity Wants Actionable Guidance

The Loan Officer

"I need to explain this AI decision to the customer and the regulator. Right now, I can't."

Needs Audit Trail Needs Confidence

The "Glass Box" Strategy

Instead of hiding the AI, we narrate it. Every credit decision becomes a story: what the AI saw, what it weighted, and what the applicant can do next. Transparency as a feature, not an afterthought.

The Action

Research, Design, and Validation

1 Discovery & Research

  • Ran 12 contextual interviews with loan officers to map their decision-making mental model
  • Conducted appeal analysis on 200+ declined applications to identify the top 5 confusion triggers
  • Ran an EU AI Act compliance audit with legal team to define minimum explainability requirements
  • Benchmarked explainability UX patterns across Stripe, Experian, and Funding Circle

Top 5 Appeal Reasons

1 "No reason given for decline" 68%
2 "Don't know what to improve" 54%
3 "Score seems inconsistent with history" 41%
4 "AI feels biased no human review" 33%
5 "Can't access decision documentation" 28%

2 Key Design Decisions

Factor Contribution Chart

A horizontal bar chart showing the top 5 factors that influenced the AI decision with plain-English labels, not ML jargon.

Credit Health Roadmap

A 3-step improvement plan generated by AI showing exactly what the SMB needs to change and what score improvement to expect.

Officer Override Audit Trail

A structured override form requiring officers to document their reasoning creating a regulator-ready audit trail for every human intervention.

The Design

Explainability as a First-Class Feature

Applicant Decision Screen

  • Decision Summary Card Plain-English verdict with a confidence indicator (e.g., "Strong Decline 94% confidence") replacing technical score outputs.
  • Top Factors Panel Colour-coded factor contributions (red = negative, green = positive) with hover tooltips explaining each factor in plain language.
  • Credit Health Roadmap AI-generated improvement plan with projected score changes for each recommended action turning rejection into a growth path.
  • Request Human Review One-click escalation to a loan officer with a pre-populated context brief reducing officer prep time by 15 minutes per case.
Application Declined

AI Confidence: 94% · Reviewed: March 2025

Top Influencing Factors

Debt-to-Revenue Ratio −38pts
Payment History (12mo) −22pts
Business Age +14pts

The Result

Transparency Built Trust and Revenue

40%
Reduction in Decision Appeals
28%
Loan Officer Confidence Increase
100%
Regulatory Audit Pass Rate
-65%
Override Rate (Officers)
"For the first time, I can sit across from an SMB client, show them exactly why the AI scored them the way it did, and walk them through what to do next. That's a game changer for client trust."

Senior Loan Officer, B2B Lending Platform